When Switching Algorithms Helps: A Theoretical Study of Online Algorithm Selection
Denis Antipov, Carola Doerr

TL;DR
This paper provides the first theoretical example demonstrating that switching between algorithms can asymptotically outperform individual algorithms, with a specific strategy achieving faster optimization times on OneMax.
Contribution
It introduces a theoretical framework showing how switching between two specific algorithms can lead to asymptotic speedups in optimization.
Findings
Switching algorithms can asymptotically outperform single algorithms.
A specific switching strategy achieves expected time $O(n ext{log} ext{log} n)$ on OneMax.
The analysis combines fixed-start and fixed-target perspectives.
Abstract
Online algorithm selection (OAS) aims to adapt the optimization process to changes in the fitness landscape and is expected to outperform any single algorithm from a given portfolio. Although this expectation is supported by numerous empirical studies, there are currently no theoretical results proving that OAS can yield asymptotic speedups (apart from some artificial examples for hyper-heuristics). Moreover, theory-based guidelines for when and how to switch between algorithms are largely missing. In this paper, we present the first theoretical example in which switching between two algorithms -- the EA and the GA -- solves the OneMax problem asymptotically faster than either algorithm used in isolation. We show that an appropriate choice of population sizes for the two algorithms allows the optimum to be reached in expected…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
